seo-technical
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external web sources which could contain malicious instructions designed to influence the agent's behavior. * Ingestion points: Content is ingested from external URLs (robots.txt, XML sitemaps, HTML source code, and security headers) during the audit process in SKILL.md. * Boundary markers: The instructions do not specify any delimiters or warnings to ignore embedded instructions within the fetched external content. * Capability inventory: The skill has capabilities to read/write local cache files in .seo-cache/ and execute local Python scripts using the shell. * Sanitization: There is no mention of sanitizing or validating the external content before it is parsed and used in the audit report.
- [COMMAND_EXECUTION]: The skill invokes local Python utility scripts (scripts/pagespeed_check.py, scripts/crux_history.py, and scripts/gsc_inspect.py) via the command line, passing user-provided URLs as arguments. This represents a standard command execution surface for external tool integration.
Audit Metadata